Papers
3
Total Citations
24
H-Index
2
About
Tao Ku is a researcher advancing the intersection of computer vision and robotic decision-making. His primary research areas include semantic segmentation for scene perception, robot hand-eye coordination, and virtual reality operating systems. Ku’s most cited work, "Multilevel Feature Fusion Dilated Convolutional Network for Semantic Segmentation" (2021, 17 citations), introduces a novel CNN architecture that fuses multilevel features to significantly improve segmentation accuracy and speed—a critical enhancement for autonomous robot scene understanding. In "Robot Hand-Eye Cooperation Based on Improved Inverse Reinforcement Learning" (2021, 5 citations), he tackles the challenge of enabling industrial robots to make precise, visually-guided action decisions, proposing a highly optimized coordination model to boost on-site adaptability. Ku’s contributions are supported by the National Key Research and Development Program of China, underscoring the national importance of his work. While a 2022 corrigendum addresses a funding error in a related virtual reality robot operating system study, his core research demonstrates a clear trajectory toward more perceptive and autonomous robotic systems. With growing citation impact, Ku is a promising voice in applied robotics and deep learning.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3